Releasesby GlyphNew serverless models
The following models are now available on serverless : elorian-labs/glimpse-1.0 : 262,144 context length, FP8 quantization, function calling, and structured outputs. Pricing: $0.60 input / $3.00 output / $0.06 cached input (per 1M tokens).
Also shipped Nov 10, 2026Together AI in November 2026 →
Amazon Bedrock AgentCore now offers a Web Search API
AWS launched the InvokeWebSearch API on Amazon Bedrock AgentCore, enabling direct web search execution billed at $7 per 1,000 queries.
Flagship - Evaluate Flagship feature flags from Rust
Cloudflare released an official Rust SDK (`cloudflare-flagship`) for Flagship, enabling async Rust applications to evaluate feature flags via OpenFeature with remote or in-process local evaluation.
BigQuery generative AI functions support gemini-4-carbon
Google Cloud announced general availability for the gemini-4-carbon model across BigQuery generative AI functions.
Amazon OpenSearch Service announces managed cross-Region disaster recovery
AWS introduced managed cross-Region disaster recovery for Amazon OpenSearch Service, providing continuous data replication with an RPO under one minute and RTO under 20 minutes.
Amazon Bedrock adds bedrock-runtime endpoint support for Daybreak models
AWS added support for OpenAI Daybreak Red and Daybreak Blue cybersecurity models on Amazon Bedrock runtime endpoints via US and Global cross-Region inference profiles.
Gemini Enterprise: Gemini 4 Carbon available in web app, mobile app, Workflow Builder, and AI developer tools
Google Cloud generally released Gemini 4 Carbon across Gemini Enterprise web and mobile apps, Workflow Builder, and AI developer tools with multi-region availability.
More from Together AI platformEvery Together AI platform release →
New serverless models
The following models are now available on serverless : thinkingmachines/Inkling-2-Small : 1,048,576 context length, NVFP4 quantization, text and image input, function calling, and structured outputs. Pricing: $0.30 input / $1.00 output / $0.03 cached input (per 1M tokens).
New serverless models
Together AI added the moonshotai/Kimi-K3.1-Pro model to its serverless platform, supporting a 1M token context window, function calling, and structured outputs.
Messages API and Responses API support more models
The Messages API and Responses API now support more models: Serverless inference: zai-org/GLM-5.3-Flash and deepseek-ai/DeepSeek-V4.1-Flash-1017 . Dedicated model inference: zai-org/GLM-5.3 and deepseek-ai/DeepSeek-V4.1-Flash-1017 .
Post-training: Kimi K3.1 Pro
Together AI now supports LoRA post-training for the Kimi K3.1 Pro model with a 163,840-token training context.
Messages API and Responses API
Together AI now supports the Anthropic Messages API at POST /v1/messages and the OpenAI Responses API at POST /v1/responses . To run an app built on either API on Together, change its API key, base URL, and model.
Post-training: FP4 preparation for MiniMax M3.1 Flash
You can now deploy a MiniMax M3.1 Flash adapter on dedicated model inference by first preparing it for FP4 inference . The base model already ships in its serving format, so the job only merges the adapter, which takes about 1 hour.
Together Python SDK and CLI 3.1.0
Together Python SDK 3.1.0 and Together CLI 3.1.0 are now available.
What's new:
- Deploy after tg login : tg beta jig deploy now works with a tg login session, so you don't need an API key to deploy a container . Expiring secrets: client.beta.jig.secrets.create and update take ttl_seconds , which sets how long a secret lives before it's deleted, from one to 14 days. Secrets return their deletion time as expires_at .